We had a healthcare claims platform stuck at 45% recall on medical coding. Not 45% on a benchmark....
When Fine-Tuning Stops Working: The Architecture Lesson That Took Our Healthcare AI From 60% to 92% Recall
Related
I tried to obfuscate my Java code before sending it to AI — here's what broke
When a client added a "no AI assistants on our codebase" clause to my contract last year, I did what...
AI Gateway Fees Compared: Who Marks Up Your Tokens?
Comparing AI gateways on price sounds simple until you read the fine print. The number on the pricing...
Prompt Caching Explained: How to Cut LLM Costs by 30–99%
The cheapest LLM request is the one you don't send. If the same question shows up twice, there's no...